HEAD TO HEAD
Make the
right call.
Pick two to four models. Compare category evidence, price, context, speed and capabilities side by side.
Sign in to save this comparison →01 / SCORECARD
Coding focus · side by side
| Metric | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| Quantum Score | 51QUANTUM SCORE | Insufficient verified data73% coverage |
| Confidence / coverage | Moderate confidence · 73% · 3 independent domains | Limited evidence · 73% · 2 independent domains |
| Context window | — tokens | 1,050,000 tokens |
| Modalities / tools | text, image · vision, tool use | text, image · tool use, vision |
| Coding | 16 | 49 +33 vs first |
| Reasoning | 62 | 52 -10 vs first |
| Math | 95 | 75 -20 vs first |
| Research | — | — |
| Agents | 60 | 20 -40 vs first |
| Multimodal | — | — |
| Speed | — | — |
| Value | 51 | 48 -3 vs first |
| Input / 1M | $0.75 | $0.10 |
| Output / 1M | $3.75 | $0.50 |
| Measured output speed | — | — |
02 / EVIDENCE
Published benchmark evidence
| Benchmark | Gemini 3.8 Flash | GPT-6 Luna |
|---|---|---|
| ARC-AGI-3 Semi-Private Standard harness best effort · 3 Semi-Private · ARC Prize Standard harness; best published effort per model | 10.3663 % benchmark maintainer ↗ | 0.1942 % benchmark maintainer ↗ |
| LiveBench code_completion · 2026-06-25 · Public table; published model effort variant | 71.739 % benchmark maintainer ↗ | 80.435 % benchmark maintainer ↗ |
| LiveBench code_generation · 2026-06-25 · Public table; published model effort variant | 73.239 % benchmark maintainer ↗ | 77.465 % benchmark maintainer ↗ |
| LiveBench javascript · 2026-06-25 · Public table; published model effort variant | 72.727 % benchmark maintainer ↗ | 63.636 % benchmark maintainer ↗ |
| LiveBench AMPS_Hard · 2026-06-25 · Public table; published model effort variant | 99 % benchmark maintainer ↗ | 98 % benchmark maintainer ↗ |
| LiveBench olympiad · 2026-06-25 · Public table; published model effort variant | 92.159 % benchmark maintainer ↗ | 90.376 % benchmark maintainer ↗ |
| LiveBench theory_of_mind · 2026-06-25 · Public table; published model effort variant | 76.923 % benchmark maintainer ↗ | 73.077 % benchmark maintainer ↗ |
| LiveBench zebra_puzzle · 2026-06-25 · Public table; published model effort variant | 98.25 % benchmark maintainer ↗ | 96 % benchmark maintainer ↗ |
AS THE EVIDENCE CHANGED
Comparison history
Dated releases, price events, and benchmark publications. A price or test change can alter the factual comparison; this timeline does not pick a winner.
2026-09-22 · GPT-6 Sol and Luna added to the API ↗ · source
2026-09-02 · Gemini 3.8 Flash released ↗ · source
2026-09-30 verified (test date not published) · gemini-3-8-flash entered LiveBench code_completion (2026-06-25) at 71.739 % · source ↗
2026-09-30 verified (test date not published) · gemini-3-8-flash entered LiveBench code_generation (2026-06-25) at 73.239 % · source ↗
2026-09-30 verified (test date not published) · gemini-3-8-flash entered LiveBench javascript (2026-06-25) at 72.727 % · source ↗
2026-09-30 verified (test date not published) · gemini-3-8-flash entered LiveBench AMPS_Hard (2026-06-25) at 99 % · source ↗
2026-09-30 verified (test date not published) · gemini-3-8-flash entered LiveBench olympiad (2026-06-25) at 92.159 % · source ↗
2026-09-30 verified (test date not published) · gemini-3-8-flash entered LiveBench theory_of_mind (2026-06-25) at 76.923 % · source ↗
2026-09-30 verified (test date not published) · gemini-3-8-flash entered LiveBench zebra_puzzle (2026-06-25) at 98.25 % · source ↗
2026-09-30 verified (test date not published) · gpt-6-luna entered LiveBench code_completion (2026-06-25) at 80.435 % · source ↗
2026-09-30 verified (test date not published) · gpt-6-luna entered LiveBench code_generation (2026-06-25) at 77.465 % · source ↗
2026-09-30 verified (test date not published) · gpt-6-luna entered LiveBench javascript (2026-06-25) at 63.636 % · source ↗
2026-09-30 verified (test date not published) · gpt-6-luna entered LiveBench AMPS_Hard (2026-06-25) at 98 % · source ↗
2026-09-30 verified (test date not published) · gpt-6-luna entered LiveBench olympiad (2026-06-25) at 90.376 % · source ↗
An overall score appears only after enough current, comparable, independently sourced results exist. Pricing and individual benchmark results remain visible meanwhile.